{"id":"W4396561900","doi":"10.3390/atmos15050564","title":"Wide and Deep Learning Model for Satellite-Based Real-Time Aerosol Retrievals in China","year":2024,"lang":"en","type":"article","venue":"Atmosphere","topic":"Atmospheric aerosols and clouds","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Interpretability; Geostationary orbit; Deep blue; Aerosol; Deep learning; Satellite; Environmental science; Remote sensing; Mean squared error; Gradient boosting; Meteorology; Computer science; Artificial intelligence; Geology; Mathematics; Geography; Statistics; Random forest","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000296737,0.000207088,0.0002181204,3.769973e-7,0.0001245759,0.00008609896,0.0001439479,0.0001299801,0.001118187],"category_scores_gemma":[0.00005935485,0.0001861452,0.00007614306,0.00027707,0.0001246458,0.0001797885,0.00008929271,0.0001921327,0.0001968183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001435862,"about_ca_system_score_gemma":0.00002427661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003257653,"about_ca_topic_score_gemma":0.000158058,"domain_scores_codex":[0.9986132,0.00003855752,0.0002481157,0.0005039744,0.0002032131,0.000392945],"domain_scores_gemma":[0.9994804,0.0001671863,0.00004540155,0.0001869059,0.000004664735,0.0001154456],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000199,0.0001101576,0.2473948,0.0001843969,0.00003315919,0.00005981343,0.002537373,0.5958711,0.01140365,0.0003566984,0.001872156,0.1399777],"study_design_scores_gemma":[0.0003711086,0.0001126503,0.01808198,0.00006076242,0.00001882672,0.000002225779,0.00007086932,0.9777768,0.000344527,0.000739727,0.002158117,0.0002624399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9713988,0.001142232,0.01746203,0.0003439645,0.00005583151,0.000394947,0.000003196348,0.0001579581,0.009041047],"genre_scores_gemma":[0.9681045,0.0003969688,0.02270666,0.0001368383,0.00002748611,0.00004591278,0.000009377489,0.00005122973,0.008521023],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3819057,"threshold_uncertainty_score":0.9997949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006569664434663874,"score_gpt":0.223596976021004,"score_spread":0.2170273115863401,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}